Data Scientist - Cleared

Responsibilities

• Design, develop, and maintain Python-based data processing pipelines for text ingestion, transformation, and enrichment.
• Develop AI-powered agentic workflows and LLM-integrated applications for data triage, classification, and analysis.
• Build reusable AI capabilities, prompt frameworks, and agent-based services for enterprise data platforms.
• Integrate and operationalize LLMs for retrieval, reasoning, summarization, and decision-support.
• Troubleshoot, optimize, and scale text-processing pipelines for data quality and system reliability.
• Design APIs and backend services connecting AI models, data pipelines, and mission applications.
• Collaborate with cross-functional teams (data scientists, software engineers, product stakeholders) to prototype and deploy AI solutions.
• Develop Python-based automation tools for data engineering, workflow orchestration, and model integration.
• Evaluate emerging AI technologies and recommend enhancements.

Requirements

• Active TS/SCI with Polygraph clearance.
• Experience with ETL on large unstructured datasets.
• Proficiency in Python.
• Experience with Apache Kafka, Apache Spark, Prefect, Docker, Kubernetes, and CI/CD pipelines.
• Solid understanding of DevOps principles (automation, monitoring, reliability).